© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 182786
    Prev
    Next
    INDEX
    Explanations

    standards to build

    np_acts-logits-general · gemini-2.5-flash-lite

    specific commands or actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     օ
    0.51
    mast
    0.50
    owls
    0.47
     மட்டும்
    0.46
     अपरा
    0.46
     سرد
    0.46
     bess
    0.44
     constante
    0.43
    이랑
    0.43
    melding
    0.43
    POSITIVE LOGITS
     Buildings
    0.48
    
    0.47
    ᓄ
    0.47
    🤵
    0.46
    িল্লী
    0.44
     bangunan
    0.44
     vál
    0.42
    Buildings
    0.42
    進入
    0.41
    Ἥ
    0.41
    Activations Density 0.001%

    No Known Activations